Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of weapons or items related to violence, such as arms and guns

    oai_token-act-pair · gpt-3.5-turbo

    references to weapons or armaments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Woodward
    -0.81
    ãĤ©
    -0.80
    DAY
    -0.74
    é¾įå
    -0.73
     Sound
    -0.70
     Dough
    -0.70
    IENCE
    -0.68
    TION
    -0.68
     Living
    -0.64
    KEY
    -0.63
    POSITIVE LOGITS
    ament
    1.11
     arms
    1.06
     arm
    0.96
    aments
    0.94
    chair
    0.86
    guards
    0.85
    chairs
    0.81
    ageddon
    0.81
     cannons
    0.78
     cannon
    0.78
    Act Density 0.010%

    No Known Activations